In the present paper,we give a systematic study of the discrete correspondence the-ory and topological correspondence theory of modal meet-implication logic and moda1 meet-semilattice logic,in the semantics provided i...In the present paper,we give a systematic study of the discrete correspondence the-ory and topological correspondence theory of modal meet-implication logic and moda1 meet-semilattice logic,in the semantics provided in[21].The special features of the present paper include the following three points:the first one is that the semantic structure used is based on a semilattice rather than an ordinary partial order,the second one is that the propositional vari-ables are interpreted as filters rather than upsets,and the nominals,which are the“first-order counterparts of propositional variables,are interpreted as principal filters rather than principal upsets;the third one is that in topological correspondence theory,the collection of admissi-ble valuations is not closed under taking disjunction,which makes the proof of the topological Ackermann 1emma different from existing settings.展开更多
In the age of big data,ensuring data privacy while enabling efficient encrypted data retrieval has become a critical challenge.Traditional searchable encryption schemes face difficulties in handling complex semantic q...In the age of big data,ensuring data privacy while enabling efficient encrypted data retrieval has become a critical challenge.Traditional searchable encryption schemes face difficulties in handling complex semantic queries.Additionally,they typically rely on honest but curious cloud servers,which introduces the risk of repudiation.Furthermore,the combined operations of search and verification increase system load,thereby reducing performance.Traditional verification mechanisms,which rely on complex hash constructions,suffer from low verification efficiency.To address these challenges,this paper proposes a blockchain-based contextual semantic-aware ciphertext retrieval scheme with efficient verification.Building on existing single and multi-keyword search methods,the scheme uses vector models to semantically train the dataset,enabling it to retain semantic information and achieve context-aware encrypted retrieval,significantly improving search accuracy.Additionally,a blockchain-based updatable master-slave chain storage model is designed,where the master chain stores encrypted keyword indexes and the slave chain stores verification information generated by zero-knowledge proofs,thus balancing system load while improving search and verification efficiency.Finally,an improved non-interactive zero-knowledge proof mechanism is introduced,reducing the computational complexity of verification and ensuring efficient validation of search results.Experimental results demonstrate that the proposed scheme offers stronger security,balanced overhead,and higher search verification efficiency.展开更多
While oceanic and coastal acidification has gained increased attention,long-term pH trends and their drivers in large freshwater systems remain poorly understood.The Laurentian Great Lakes are the world’s largest fre...While oceanic and coastal acidification has gained increased attention,long-term pH trends and their drivers in large freshwater systems remain poorly understood.The Laurentian Great Lakes are the world’s largest freshwater system,and in many ways resemble marine ecosystems.However,unlike the open ocean and coastal waters where pH has declined due to rising atmospheric CO_(2),no significant pH trends have been observed in the Laurentian Great Lakes,despite significant ecosystem changes driven partly by the invasion of dreissenid mussels.This study examined 41 years of field observations from Lake Michigan to investigate the long-term carbonate chemistry dynamics.Observational results revealed substantial declines in both total alkalinity(TA)and dissolved inorganic carbon(DIC)over the four decades.Mussel shell calcification emerged as the primary mechanism behind these declines,accounting for 97%and 47%of the observed changes in TA and DIC,respectively,lowering water column pH by 0.24 units.Elevated carbon accumulation in soft mussel tissues,coupled with long-term changes in the air-water pCO_(2)gradient during summer,significantly contributed to long-term DIC variations,explaining 18%and 28%of the lake-wide DIC loss.These two mechanisms also resulted in an overall pH increase of 0.09 and 0.12 units,largely offsetting the calcification-driven pH decrease.These findings bridge a gap in acidification research for large freshwater systems and provide valuable insights for comprehensive lake-wide management strategies.展开更多
High-resolution remote sensing images(HRSIs)are now an essential data source for gathering surface information due to advancements in remote sensing data capture technologies.However,their significant scale changes an...High-resolution remote sensing images(HRSIs)are now an essential data source for gathering surface information due to advancements in remote sensing data capture technologies.However,their significant scale changes and wealth of spatial details pose challenges for semantic segmentation.While convolutional neural networks(CNNs)excel at capturing local features,they are limited in modeling long-range dependencies.Conversely,transformers utilize multihead self-attention to integrate global context effectively,but this approach often incurs a high computational cost.This paper proposes a global-local multiscale context network(GLMCNet)to extract both global and local multiscale contextual information from HRSIs.A detail-enhanced filtering module(DEFM)is proposed at the end of the encoder to refine the encoder outputs further,thereby enhancing the key details extracted by the encoder and effectively suppressing redundant information.In addition,a global-local multiscale transformer block(GLMTB)is proposed in the decoding stage to enable the modeling of rich multiscale global and local information.We also design a stair fusion mechanism to transmit deep semantic information from deep to shallow layers progressively.Finally,we propose the semantic awareness enhancement module(SAEM),which further enhances the representation of multiscale semantic features through spatial attention and covariance channel attention.Extensive ablation analyses and comparative experiments were conducted to evaluate the performance of the proposed method.Specifically,our method achieved a mean Intersection over Union(mIoU)of 86.89%on the ISPRS Potsdam dataset and 84.34%on the ISPRS Vaihingen dataset,outperforming existing models such as ABCNet and BANet.展开更多
Advanced traffic monitoring systems encounter substantial challenges in vehicle detection and classification due to the limitations of conventional methods,which often demand extensive computational resources and stru...Advanced traffic monitoring systems encounter substantial challenges in vehicle detection and classification due to the limitations of conventional methods,which often demand extensive computational resources and struggle with diverse data acquisition techniques.This research presents a novel approach for vehicle classification and recognition in aerial image sequences,integrating multiple advanced techniques to enhance detection accuracy.The proposed model begins with preprocessing using Multiscale Retinex(MSR)to enhance image quality,followed by Expectation-Maximization(EM)Segmentation for precise foreground object identification.Vehicle detection is performed using the state-of-the-art YOLOv10 framework,while feature extraction incorporates Maximally Stable Extremal Regions(MSER),Dense Scale-Invariant Feature Transform(Dense SIFT),and Zernike Moments Features to capture distinct object characteristics.Feature optimization is further refined through a Hybrid Swarm-based Optimization algorithm,ensuring optimal feature selection for improved classification performance.The final classification is conducted using a Vision Transformer,leveraging its robust learning capabilities for enhanced accuracy.Experimental evaluations on benchmark datasets,including UAVDT and the Unmanned Aerial Vehicle Intruder Dataset(UAVID),demonstrate the superiority of the proposed approach,achieving an accuracy of 94.40%on UAVDT and 93.57%on UAVID.The results highlight the efficacy of the model in significantly enhancing vehicle detection and classification in aerial imagery,outperforming existing methodologies and offering a statistically validated improvement for intelligent traffic monitoring systems compared to existing approaches.展开更多
AIM:To investigate the long-term outcomes in acute primary angle closure(APAC)patients treated with lens extraction(LE)surgery and to identify risk factors for glaucomatous optic neuropathy(GON).METHODS:In this longit...AIM:To investigate the long-term outcomes in acute primary angle closure(APAC)patients treated with lens extraction(LE)surgery and to identify risk factors for glaucomatous optic neuropathy(GON).METHODS:In this longitudinal observational study,detailed medical histories of APAC patients and comprehensive ophthalmic examinations at final followup were collected.Logistic regression analysis was performed to identify predictors of blindness.Univariate and multivariate linear regression analyses were conducted to determine risk factors associated with visual outcomes.RESULTS:This study included 39 affected eyes of 31 subjects(26 females)with an average age of 74.1±8.0y.At 6.7±4.2y after APAC attack,2(5.7%)eyes had bestcorrected visual acuity(VA)worse than 3/60.Advanced glaucomatous visual field loss was observed in 15(39.5%)affected eyes and 5(25.0%)fellow eyes.Nine affected eyes(23.7%)had GON,and 11(28.9%)were blind.Six(15.4%)affected eyes and 2(9.1%)fellow eyes had suspicious progression.A significantly higher blindness rate in factory workers compared to office workers.Logistic regression identified that worse VA at attack(OR 10.568,95%CI 1.288-86.695;P=0.028)and worse early postoperative VA(OR 13.214,95%CI 1.157-150.881;P=0.038)were risk factors for blindness.Multivariate regression showed that longer duration of elevated intraocular pressure(P=0.004)and worse early postoperative VA(P=0.009)were associated with worse visual outcomes.CONCLUSION:Despite LE surgery,some APAC patients experience continued visual function deterioration.Lifelong monitoring is necessary.Target pressure and progression rates should be re-evaluated during follow-up.展开更多
Long-term manure application has the potential to alleviate soil acidification, and increase carbon sequestration and nutrient availability, thus improving cropland fertility. However, the mechanisms behind greenhouse...Long-term manure application has the potential to alleviate soil acidification, and increase carbon sequestration and nutrient availability, thus improving cropland fertility. However, the mechanisms behind greenhouse gas N_(2)O emissions from acidic soil mediated by long-term manure application remain poorly understood. Herein, we investigated N_(2)O emission and its linkage with gross N mineralization and nitrification rates, as well as nitrifying and denitrifying microbes in an acidic upland soil subjected to 36-year fertilization treatments, including an unfertilized control(CK), inorganic fertilizer(F), 2× rate of inorganic fertilizer(2F), manure(M), and the combination of inorganic fertilizer and manure(FM) treatments. Compared to the CK treatment(1.34 μg N kg^(-1) d^(-1)), fertilization strongly increased N_(2)O emissions by 34-fold on average, with more pronounced increases in the manure-amendment(10.6-169 μg N kg^(-1) d^(-1)) than those in the inorganic fertilizer treatments(3.26-5.51 μg N kg^(-1) d^(-1)). The manure amendment-stimulated N_(2)O emissions were highly associated with increased soil pH, mean weight diameter of soil aggregates, substrate availability(e.g., particulate organic carbon, NO_(3)^(-)and available phosphorus), gross N mineralization rates, denitrifier abundances and the(nirK+nirS)/nosZ ratio. These findings suggest that the increased N_(2)O emissions primarily resulted from alleviated acidification, increased substrate availability and improved soil structure, thus enhancing microbial N mineralization and favoring N_(2)O^(-)producing denitrifiers over N_(2)O consumers. Moreover, ammonia-oxidizing bacteria(AOB) rather than ammonia-oxidizing archaea(AOA) positively correlated with soil NO_(3)^(-)concentration and N_(2)O emissions, indicating that nitrification indirectly contributed to N_(2)O production by supplying NO_(3)^(-)for denitrification. Collectively, manure amendment potentially stimulates N_(2)O emissions, primarily resulting from alleviated soil acidification and increased substrate availability, thus enhancing N mineralization and denitrifier-mediated N_(2)O production. Our findings suggest that consideration should be given to the greenhouse gas budgets of agricultural ecosystems when applying manure for managing the pH and fertility of acidic soils.展开更多
This paper proposes a collaborative design model based on operation semantics in a distributed computer-aided design (CAD) environment. The goal is to reduce time consumption in data format conversion and the requirem...This paper proposes a collaborative design model based on operation semantics in a distributed computer-aided design (CAD) environment. The goal is to reduce time consumption in data format conversion and the requirement of network bandwidth so as to improve the cooperative ability and the synchronization efficiency. Firstly, real-time collaborative design is reviewed and three kinds of real-time collaborative design models are discussed. Secondly, the concept of operation semantics is defined and the framework of an operation semantics model is presented. The operation semantics carries the original design data and actual operation process to express design intent and operation activity in conventional CAD systems. Finally, according to the operation semantics model, a CAD operation primitive is defined which can be retrieved from and mapped to the local CAD system operation commands; a distributed CAD collaborative architecture based on the model is presented, and an example is given to verify the model.展开更多
A global semantics matching and QoS-awareness service selection are proposed when aimed at a web services composition process.Both QoS-aware matching and global semantic matching are considered during the global match...A global semantics matching and QoS-awareness service selection are proposed when aimed at a web services composition process.Both QoS-aware matching and global semantic matching are considered during the global matching.When there are demands for global semantic matching and QoS of service composition,a concrete service set which meets the demands is selected for the whole service composition process and an optimal solution is also achieved.A QoS model is built and the corresponding evaluation method is given for the matching of the service composition process.Based on them,a genetic algorithm is proposed to achieve the maximal global semantic matching degree and fulfill the QoS requirements for the whole service composition process.Experimental results and analysis show that the algorithm is feasible and effective for semantics and QoS-aware service matching.展开更多
What and how we translate are questions often argued about. No matter what kind of answers one may give, priority in translation should be granted to meaning, especially those meanings that exist in all concerned lang...What and how we translate are questions often argued about. No matter what kind of answers one may give, priority in translation should be granted to meaning, especially those meanings that exist in all concerned languages. This research defines them as universal sememes, and the study of them as universal semantics, of which applications are also briefly looked into.展开更多
Fine-grained image classification, which aims to distinguish images with subtle distinctions, is a challenging task for two main reasons: lack of sufficient training data for every class and difficulty in learning dis...Fine-grained image classification, which aims to distinguish images with subtle distinctions, is a challenging task for two main reasons: lack of sufficient training data for every class and difficulty in learning discriminative features for representation. In this paper, to address the two issues, we propose a two-phase framework for recognizing images from unseen fine-grained classes, i.e., zeroshot fine-grained classification. In the first feature learning phase, we finetune deep convolutional neural networks using hierarchical semantic structure among fine-grained classes to extract discriminative deep visual features. Meanwhile, a domain adaptation structure is induced into deep convolutional neural networks to avoid domain shift from training data to test data. In the second label inference phase, a semantic directed graph is constructed over attributes of fine-grained classes. Based on this graph, we develop a label propagation algorithm to infer the labels of images in the unseen classes. Experimental results on two benchmark datasets demonstrate that our model outperforms the state-of-the-art zero-shot learning models. In addition, the features obtained by our feature learning model also yield significant gains when they are used by other zero-shot learning models, which shows the flexility of our model in zero-shot finegrained classification.展开更多
In Chinese question answering system, because there is more semantic relation in questions than that in query words, the precision can be improved by expanding query while using natural language questions to retrieve ...In Chinese question answering system, because there is more semantic relation in questions than that in query words, the precision can be improved by expanding query while using natural language questions to retrieve documents. This paper proposes a new approach to query expansion based on semantics and statistics Firstly automatic relevance feedback method is used to generate a candidate expansion word set. Then the expanded query words are selected from the set based on the semantic similarity and seman- tic relevancy between the candidate words and the original words. Experiments show the new approach is effective for Web retrieval and out-performs the conventional expansion approaches.展开更多
Spatio-temporal semantics based on ＂object views＂ or ＂event views＂ has few abilities to represent and model the continuity and gradual oceanic phenomena or objects, which seriously limits the specific marine appli...Spatio-temporal semantics based on ＂object views＂ or ＂event views＂ has few abilities to represent and model the continuity and gradual oceanic phenomena or objects, which seriously limits the specific marine applications and knowledge discovery and data mining, so this paper proposes a hierarchical abstraction semantics with ＂marine spatio-temporal process-life span phases-evolution sequences--state units＂ and process objects included by level with ＂marine process objects--phase objects--sequence object---state objects＂ with the oceanic process characteristics into the marine process semantics. In addition, this paper designs the storage and representation of marine process objects using the backus normal forms （BNF） and abstract data type （ADT）. Base on E1 Nifio Southern Oscilation （ENSO） index and Chinese rain gauging station data, this paper also gives a case of study. The spatio-temporal analysis between ENSO process and Chinese rainfall anomalies shows that the marine spatio-temporal semantics not only can illustrate the spatial distribution of Chinese rainfall anomalies in different time scales at ENSO process, life span phases and state units, but also analyze the dynamic changes of Chinese rainfall anomalies in different life span phases or state units within ENSO evolution.展开更多
There are mainly four kinds of models to record and deal with historical information.By taking them as reference,the spatio-temporal model based on event semantics is proposed.In this model,according to the way for de...There are mainly four kinds of models to record and deal with historical information.By taking them as reference,the spatio-temporal model based on event semantics is proposed.In this model,according to the way for describing an event,all the information are divided into five domains.This paper describes the model by using the land parcel change in the cadastral information system,and expounds the model by using five tables corresponding to the five domains.With the aid of this model,seven examples are given on historical query,trace back and recurrence.This model can be implemented either in the extended relational database or in the object-oriented database.展开更多
In this work, in order to improve spatial recognition abilities for the long-term operation tasks of the assistant robot for the elderly, a novel approach of semantic region estimation is proposed. We define a novel g...In this work, in order to improve spatial recognition abilities for the long-term operation tasks of the assistant robot for the elderly, a novel approach of semantic region estimation is proposed. We define a novel graphbased semantic region descriptions, which are estimated in a dynamically fashion. We propose a two-level update algorithm, namely, Symbols update level and Regions update level. The algorithm firstly adopts particle filter to update weights of the symbols, and then use the Viterbi algorithm to estimate the region the robot stays in based on those weights, optimally. Experimental results demonstrate that our proposed approach can solve problems of the long-term operation and kidnapped robot problem.展开更多
Existing multi-view three-dimensional(3 D) reconstruction methods can only capture single type of feature from input view, failing to obtain fine-grained semantics for reconstructing the complex shapes. They rarely ex...Existing multi-view three-dimensional(3 D) reconstruction methods can only capture single type of feature from input view, failing to obtain fine-grained semantics for reconstructing the complex shapes. They rarely explore the semantic association between input views, leading to a rough 3 D shape. To address these challenges, we propose a semantics-aware transformer(SATF) for 3 D reconstruction. It is composed of two parallel view transformer encoders and a point cloud transformer decoder, and takes two red, green and blue(RGB) images as input and outputs a dense point cloud with richer details. Each view transformer encoder can learn a multi-level feature, facilitating characterizing fine-grained semantics from input view. The point cloud transformer decoder explores a semantically-associated feature by aligning the semantics of two input views, which describes the semantic association between views. Furthermore, it can generate a sparse point cloud using the semantically-associated feature. At last, the decoder enriches the sparse point cloud for producing a dense point cloud with richer details. Extensive experiments on the Shape Net dataset show that our SATF outperforms the state-of-the-art methods.展开更多
Scene perception and trajectory forecasting are two fundamental challenges that are crucial to a safe and reliable autonomous driving(AD)system.However,most proposed methods aim at addressing one of the two challenges...Scene perception and trajectory forecasting are two fundamental challenges that are crucial to a safe and reliable autonomous driving(AD)system.However,most proposed methods aim at addressing one of the two challenges mentioned above with a single model.To tackle this dilemma,this paper proposes spatio-temporal semantics and interaction graph aggregation for multi-agent perception and trajectory forecasting(STSIGMA),an efficient end-to-end method to jointly and accurately perceive the AD environment and forecast the trajectories of the surrounding traffic agents within a unified framework.ST-SIGMA adopts a trident encoder-decoder architecture to learn scene semantics and agent interaction information on bird’s-eye view(BEV)maps simultaneously.Specifically,an iterative aggregation network is first employed as the scene semantic encoder(SSE)to learn diverse scene information.To preserve dynamic interactions of traffic agents,ST-SIGMA further exploits a spatio-temporal graph network as the graph interaction encoder.Meanwhile,a simple yet efficient feature fusion method to fuse semantic and interaction features into a unified feature space as the input to a novel hierarchical aggregation decoder for downstream prediction tasks is designed.Extensive experiments on the nuScenes data set have demonstrated that the proposed ST-SIGMA achieves significant improvements compared to the state-of-theart(SOTA)methods in terms of scene perception and trajectory forecasting,respectively.Therefore,the proposed approach outperforms SOTA in terms of model generalisation and robustness and is therefore more feasible for deployment in realworld AD scenarios.展开更多
基金supported by the Chinese Ministry of Education of Humanities and Social Science Project(23YJC72040003)the Key Project of Chinese Ministry of Education(22JJD720021)supported by the Natural Science Foundation of Shandong Province,China(project number:ZR2023QF021)。
文摘In the present paper,we give a systematic study of the discrete correspondence the-ory and topological correspondence theory of modal meet-implication logic and moda1 meet-semilattice logic,in the semantics provided in[21].The special features of the present paper include the following three points:the first one is that the semantic structure used is based on a semilattice rather than an ordinary partial order,the second one is that the propositional vari-ables are interpreted as filters rather than upsets,and the nominals,which are the“first-order counterparts of propositional variables,are interpreted as principal filters rather than principal upsets;the third one is that in topological correspondence theory,the collection of admissi-ble valuations is not closed under taking disjunction,which makes the proof of the topological Ackermann 1emma different from existing settings.
基金supported in part by the National Natural Science Foundation of China under Grant 62262073in part by the Yunnan Provincial Ten Thousand People Program for Young Top Talents under Grant YNWR-QNBJ-2019-237in part by the Yunnan Provincial Major Science and Technology Special Program under Grant 202402AD080002.
文摘In the age of big data,ensuring data privacy while enabling efficient encrypted data retrieval has become a critical challenge.Traditional searchable encryption schemes face difficulties in handling complex semantic queries.Additionally,they typically rely on honest but curious cloud servers,which introduces the risk of repudiation.Furthermore,the combined operations of search and verification increase system load,thereby reducing performance.Traditional verification mechanisms,which rely on complex hash constructions,suffer from low verification efficiency.To address these challenges,this paper proposes a blockchain-based contextual semantic-aware ciphertext retrieval scheme with efficient verification.Building on existing single and multi-keyword search methods,the scheme uses vector models to semantically train the dataset,enabling it to retain semantic information and achieve context-aware encrypted retrieval,significantly improving search accuracy.Additionally,a blockchain-based updatable master-slave chain storage model is designed,where the master chain stores encrypted keyword indexes and the slave chain stores verification information generated by zero-knowledge proofs,thus balancing system load while improving search and verification efficiency.Finally,an improved non-interactive zero-knowledge proof mechanism is introduced,reducing the computational complexity of verification and ensuring efficient validation of search results.Experimental results demonstrate that the proposed scheme offers stronger security,balanced overhead,and higher search verification efficiency.
基金Supported by the National Natural Science Foundation of China(No.43277051)the Key Laboratory of Integrated Regulation and Resources Development of Shallow Lakes of Ministry of Education(No.B230203006).
文摘While oceanic and coastal acidification has gained increased attention,long-term pH trends and their drivers in large freshwater systems remain poorly understood.The Laurentian Great Lakes are the world’s largest freshwater system,and in many ways resemble marine ecosystems.However,unlike the open ocean and coastal waters where pH has declined due to rising atmospheric CO_(2),no significant pH trends have been observed in the Laurentian Great Lakes,despite significant ecosystem changes driven partly by the invasion of dreissenid mussels.This study examined 41 years of field observations from Lake Michigan to investigate the long-term carbonate chemistry dynamics.Observational results revealed substantial declines in both total alkalinity(TA)and dissolved inorganic carbon(DIC)over the four decades.Mussel shell calcification emerged as the primary mechanism behind these declines,accounting for 97%and 47%of the observed changes in TA and DIC,respectively,lowering water column pH by 0.24 units.Elevated carbon accumulation in soft mussel tissues,coupled with long-term changes in the air-water pCO_(2)gradient during summer,significantly contributed to long-term DIC variations,explaining 18%and 28%of the lake-wide DIC loss.These two mechanisms also resulted in an overall pH increase of 0.09 and 0.12 units,largely offsetting the calcification-driven pH decrease.These findings bridge a gap in acidification research for large freshwater systems and provide valuable insights for comprehensive lake-wide management strategies.
基金provided by the Science Research Project of Hebei Education Department under grant No.BJK2024115.
文摘High-resolution remote sensing images(HRSIs)are now an essential data source for gathering surface information due to advancements in remote sensing data capture technologies.However,their significant scale changes and wealth of spatial details pose challenges for semantic segmentation.While convolutional neural networks(CNNs)excel at capturing local features,they are limited in modeling long-range dependencies.Conversely,transformers utilize multihead self-attention to integrate global context effectively,but this approach often incurs a high computational cost.This paper proposes a global-local multiscale context network(GLMCNet)to extract both global and local multiscale contextual information from HRSIs.A detail-enhanced filtering module(DEFM)is proposed at the end of the encoder to refine the encoder outputs further,thereby enhancing the key details extracted by the encoder and effectively suppressing redundant information.In addition,a global-local multiscale transformer block(GLMTB)is proposed in the decoding stage to enable the modeling of rich multiscale global and local information.We also design a stair fusion mechanism to transmit deep semantic information from deep to shallow layers progressively.Finally,we propose the semantic awareness enhancement module(SAEM),which further enhances the representation of multiscale semantic features through spatial attention and covariance channel attention.Extensive ablation analyses and comparative experiments were conducted to evaluate the performance of the proposed method.Specifically,our method achieved a mean Intersection over Union(mIoU)of 86.89%on the ISPRS Potsdam dataset and 84.34%on the ISPRS Vaihingen dataset,outperforming existing models such as ABCNet and BANet.
文摘Advanced traffic monitoring systems encounter substantial challenges in vehicle detection and classification due to the limitations of conventional methods,which often demand extensive computational resources and struggle with diverse data acquisition techniques.This research presents a novel approach for vehicle classification and recognition in aerial image sequences,integrating multiple advanced techniques to enhance detection accuracy.The proposed model begins with preprocessing using Multiscale Retinex(MSR)to enhance image quality,followed by Expectation-Maximization(EM)Segmentation for precise foreground object identification.Vehicle detection is performed using the state-of-the-art YOLOv10 framework,while feature extraction incorporates Maximally Stable Extremal Regions(MSER),Dense Scale-Invariant Feature Transform(Dense SIFT),and Zernike Moments Features to capture distinct object characteristics.Feature optimization is further refined through a Hybrid Swarm-based Optimization algorithm,ensuring optimal feature selection for improved classification performance.The final classification is conducted using a Vision Transformer,leveraging its robust learning capabilities for enhanced accuracy.Experimental evaluations on benchmark datasets,including UAVDT and the Unmanned Aerial Vehicle Intruder Dataset(UAVID),demonstrate the superiority of the proposed approach,achieving an accuracy of 94.40%on UAVDT and 93.57%on UAVID.The results highlight the efficacy of the model in significantly enhancing vehicle detection and classification in aerial imagery,outperforming existing methodologies and offering a statistically validated improvement for intelligent traffic monitoring systems compared to existing approaches.
文摘AIM:To investigate the long-term outcomes in acute primary angle closure(APAC)patients treated with lens extraction(LE)surgery and to identify risk factors for glaucomatous optic neuropathy(GON).METHODS:In this longitudinal observational study,detailed medical histories of APAC patients and comprehensive ophthalmic examinations at final followup were collected.Logistic regression analysis was performed to identify predictors of blindness.Univariate and multivariate linear regression analyses were conducted to determine risk factors associated with visual outcomes.RESULTS:This study included 39 affected eyes of 31 subjects(26 females)with an average age of 74.1±8.0y.At 6.7±4.2y after APAC attack,2(5.7%)eyes had bestcorrected visual acuity(VA)worse than 3/60.Advanced glaucomatous visual field loss was observed in 15(39.5%)affected eyes and 5(25.0%)fellow eyes.Nine affected eyes(23.7%)had GON,and 11(28.9%)were blind.Six(15.4%)affected eyes and 2(9.1%)fellow eyes had suspicious progression.A significantly higher blindness rate in factory workers compared to office workers.Logistic regression identified that worse VA at attack(OR 10.568,95%CI 1.288-86.695;P=0.028)and worse early postoperative VA(OR 13.214,95%CI 1.157-150.881;P=0.038)were risk factors for blindness.Multivariate regression showed that longer duration of elevated intraocular pressure(P=0.004)and worse early postoperative VA(P=0.009)were associated with worse visual outcomes.CONCLUSION:Despite LE surgery,some APAC patients experience continued visual function deterioration.Lifelong monitoring is necessary.Target pressure and progression rates should be re-evaluated during follow-up.
基金financially supported by the National Science & Technology Fundamental Resources Investigation Project of China (2021FY100501)the Youth Innovation of Chinese Academy of Agricultural Sciences (Y2023QC16)。
文摘Long-term manure application has the potential to alleviate soil acidification, and increase carbon sequestration and nutrient availability, thus improving cropland fertility. However, the mechanisms behind greenhouse gas N_(2)O emissions from acidic soil mediated by long-term manure application remain poorly understood. Herein, we investigated N_(2)O emission and its linkage with gross N mineralization and nitrification rates, as well as nitrifying and denitrifying microbes in an acidic upland soil subjected to 36-year fertilization treatments, including an unfertilized control(CK), inorganic fertilizer(F), 2× rate of inorganic fertilizer(2F), manure(M), and the combination of inorganic fertilizer and manure(FM) treatments. Compared to the CK treatment(1.34 μg N kg^(-1) d^(-1)), fertilization strongly increased N_(2)O emissions by 34-fold on average, with more pronounced increases in the manure-amendment(10.6-169 μg N kg^(-1) d^(-1)) than those in the inorganic fertilizer treatments(3.26-5.51 μg N kg^(-1) d^(-1)). The manure amendment-stimulated N_(2)O emissions were highly associated with increased soil pH, mean weight diameter of soil aggregates, substrate availability(e.g., particulate organic carbon, NO_(3)^(-)and available phosphorus), gross N mineralization rates, denitrifier abundances and the(nirK+nirS)/nosZ ratio. These findings suggest that the increased N_(2)O emissions primarily resulted from alleviated acidification, increased substrate availability and improved soil structure, thus enhancing microbial N mineralization and favoring N_(2)O^(-)producing denitrifiers over N_(2)O consumers. Moreover, ammonia-oxidizing bacteria(AOB) rather than ammonia-oxidizing archaea(AOA) positively correlated with soil NO_(3)^(-)concentration and N_(2)O emissions, indicating that nitrification indirectly contributed to N_(2)O production by supplying NO_(3)^(-)for denitrification. Collectively, manure amendment potentially stimulates N_(2)O emissions, primarily resulting from alleviated soil acidification and increased substrate availability, thus enhancing N mineralization and denitrifier-mediated N_(2)O production. Our findings suggest that consideration should be given to the greenhouse gas budgets of agricultural ecosystems when applying manure for managing the pH and fertility of acidic soils.
文摘This paper proposes a collaborative design model based on operation semantics in a distributed computer-aided design (CAD) environment. The goal is to reduce time consumption in data format conversion and the requirement of network bandwidth so as to improve the cooperative ability and the synchronization efficiency. Firstly, real-time collaborative design is reviewed and three kinds of real-time collaborative design models are discussed. Secondly, the concept of operation semantics is defined and the framework of an operation semantics model is presented. The operation semantics carries the original design data and actual operation process to express design intent and operation activity in conventional CAD systems. Finally, according to the operation semantics model, a CAD operation primitive is defined which can be retrieved from and mapped to the local CAD system operation commands; a distributed CAD collaborative architecture based on the model is presented, and an example is given to verify the model.
基金Specialized Research Fund for the Doctoral Program of Higher Education(No.20050288015)Innovation Funds of Nanjing University of Science and Technology
文摘A global semantics matching and QoS-awareness service selection are proposed when aimed at a web services composition process.Both QoS-aware matching and global semantic matching are considered during the global matching.When there are demands for global semantic matching and QoS of service composition,a concrete service set which meets the demands is selected for the whole service composition process and an optimal solution is also achieved.A QoS model is built and the corresponding evaluation method is given for the matching of the service composition process.Based on them,a genetic algorithm is proposed to achieve the maximal global semantic matching degree and fulfill the QoS requirements for the whole service composition process.Experimental results and analysis show that the algorithm is feasible and effective for semantics and QoS-aware service matching.
文摘What and how we translate are questions often argued about. No matter what kind of answers one may give, priority in translation should be granted to meaning, especially those meanings that exist in all concerned languages. This research defines them as universal sememes, and the study of them as universal semantics, of which applications are also briefly looked into.
基金supported by National Basic Research Program of China (973 Program) (No. 2015CB352502)National Nature Science Foundation of China (No. 61573026)Beijing Nature Science Foundation (No. L172037)
文摘Fine-grained image classification, which aims to distinguish images with subtle distinctions, is a challenging task for two main reasons: lack of sufficient training data for every class and difficulty in learning discriminative features for representation. In this paper, to address the two issues, we propose a two-phase framework for recognizing images from unseen fine-grained classes, i.e., zeroshot fine-grained classification. In the first feature learning phase, we finetune deep convolutional neural networks using hierarchical semantic structure among fine-grained classes to extract discriminative deep visual features. Meanwhile, a domain adaptation structure is induced into deep convolutional neural networks to avoid domain shift from training data to test data. In the second label inference phase, a semantic directed graph is constructed over attributes of fine-grained classes. Based on this graph, we develop a label propagation algorithm to infer the labels of images in the unseen classes. Experimental results on two benchmark datasets demonstrate that our model outperforms the state-of-the-art zero-shot learning models. In addition, the features obtained by our feature learning model also yield significant gains when they are used by other zero-shot learning models, which shows the flexility of our model in zero-shot finegrained classification.
基金the Specialized Research Program Fundthe Doctoral Program of Higher Education of China (20050007023)the Natural Science Foundation of Shandong Province(Y2004G04)
文摘In Chinese question answering system, because there is more semantic relation in questions than that in query words, the precision can be improved by expanding query while using natural language questions to retrieve documents. This paper proposes a new approach to query expansion based on semantics and statistics Firstly automatic relevance feedback method is used to generate a candidate expansion word set. Then the expanded query words are selected from the set based on the semantic similarity and seman- tic relevancy between the candidate words and the original words. Experiments show the new approach is effective for Web retrieval and out-performs the conventional expansion approaches.
基金The National Basic Research Program of China under contract No.2009CB723903the National Natural Science Foundation of China under contract Nos 40901194 and 40801162+2 种基金the Director Foundation of CEODECASunder contract No.Y2ZZ06101B
文摘Spatio-temporal semantics based on ＂object views＂ or ＂event views＂ has few abilities to represent and model the continuity and gradual oceanic phenomena or objects, which seriously limits the specific marine applications and knowledge discovery and data mining, so this paper proposes a hierarchical abstraction semantics with ＂marine spatio-temporal process-life span phases-evolution sequences--state units＂ and process objects included by level with ＂marine process objects--phase objects--sequence object---state objects＂ with the oceanic process characteristics into the marine process semantics. In addition, this paper designs the storage and representation of marine process objects using the backus normal forms （BNF） and abstract data type （ADT）. Base on E1 Nifio Southern Oscilation （ENSO） index and Chinese rain gauging station data, this paper also gives a case of study. The spatio-temporal analysis between ENSO process and Chinese rainfall anomalies shows that the marine spatio-temporal semantics not only can illustrate the spatial distribution of Chinese rainfall anomalies in different time scales at ENSO process, life span phases and state units, but also analyze the dynamic changes of Chinese rainfall anomalies in different life span phases or state units within ENSO evolution.
文摘There are mainly four kinds of models to record and deal with historical information.By taking them as reference,the spatio-temporal model based on event semantics is proposed.In this model,according to the way for describing an event,all the information are divided into five domains.This paper describes the model by using the land parcel change in the cadastral information system,and expounds the model by using five tables corresponding to the five domains.With the aid of this model,seven examples are given on historical query,trace back and recurrence.This model can be implemented either in the extended relational database or in the object-oriented database.
基金supported by the National Natural Science Foundation of China (61305103 and 61473103)the Foundation for Innovative Research Groups of the National Natural Science Foundation of China (51521003 )+1 种基金the Natural Science Foundation of Heilongjiang Province, China (QC2014C072 and F2015010)SelfPlanned Task (SKLRS201609B and SKLRS201411B) of State Key Laboratory of Robotics and System (HIT)
文摘In this work, in order to improve spatial recognition abilities for the long-term operation tasks of the assistant robot for the elderly, a novel approach of semantic region estimation is proposed. We define a novel graphbased semantic region descriptions, which are estimated in a dynamically fashion. We propose a two-level update algorithm, namely, Symbols update level and Regions update level. The algorithm firstly adopts particle filter to update weights of the symbols, and then use the Viterbi algorithm to estimate the region the robot stays in based on those weights, optimally. Experimental results demonstrate that our proposed approach can solve problems of the long-term operation and kidnapped robot problem.
基金supported by the National Key R&D Program of China (No.2018YFB1305200)the National Natural Science Foundation of China (Nos.61906134, 62020106004, 92048301, and 61925201)
文摘Existing multi-view three-dimensional(3 D) reconstruction methods can only capture single type of feature from input view, failing to obtain fine-grained semantics for reconstructing the complex shapes. They rarely explore the semantic association between input views, leading to a rough 3 D shape. To address these challenges, we propose a semantics-aware transformer(SATF) for 3 D reconstruction. It is composed of two parallel view transformer encoders and a point cloud transformer decoder, and takes two red, green and blue(RGB) images as input and outputs a dense point cloud with richer details. Each view transformer encoder can learn a multi-level feature, facilitating characterizing fine-grained semantics from input view. The point cloud transformer decoder explores a semantically-associated feature by aligning the semantics of two input views, which describes the semantic association between views. Furthermore, it can generate a sparse point cloud using the semantically-associated feature. At last, the decoder enriches the sparse point cloud for producing a dense point cloud with richer details. Extensive experiments on the Shape Net dataset show that our SATF outperforms the state-of-the-art methods.
基金Basic and Advanced Research Projects of CSTC,Grant/Award Number:cstc2019jcyj-zdxmX0008Science and Technology Research Program of Chongqing Municipal Education Commission,Grant/Award Numbers:KJQN202100634,KJZDK201900605National Natural Science Foundation of China,Grant/Award Number:62006065。
文摘Scene perception and trajectory forecasting are two fundamental challenges that are crucial to a safe and reliable autonomous driving(AD)system.However,most proposed methods aim at addressing one of the two challenges mentioned above with a single model.To tackle this dilemma,this paper proposes spatio-temporal semantics and interaction graph aggregation for multi-agent perception and trajectory forecasting(STSIGMA),an efficient end-to-end method to jointly and accurately perceive the AD environment and forecast the trajectories of the surrounding traffic agents within a unified framework.ST-SIGMA adopts a trident encoder-decoder architecture to learn scene semantics and agent interaction information on bird’s-eye view(BEV)maps simultaneously.Specifically,an iterative aggregation network is first employed as the scene semantic encoder(SSE)to learn diverse scene information.To preserve dynamic interactions of traffic agents,ST-SIGMA further exploits a spatio-temporal graph network as the graph interaction encoder.Meanwhile,a simple yet efficient feature fusion method to fuse semantic and interaction features into a unified feature space as the input to a novel hierarchical aggregation decoder for downstream prediction tasks is designed.Extensive experiments on the nuScenes data set have demonstrated that the proposed ST-SIGMA achieves significant improvements compared to the state-of-theart(SOTA)methods in terms of scene perception and trajectory forecasting,respectively.Therefore,the proposed approach outperforms SOTA in terms of model generalisation and robustness and is therefore more feasible for deployment in realworld AD scenarios.
